Analysis of Machine Learning Techniques for Sentinel-2A Satellite Images

Table 7

Overall accuracy for classifiers with Sentinel-2A satellite.

	Type of strategies	Classifier	Accuracy (%)
1	Object-based	RF	99.92
		KNN	91.56
2	Rule-based	DTC	91.49
3	Pixel-based	SVM	84.56
		Mahalanobis	83.83
		MLC	83.26
		Normal Bayes	83.26
		Maximum Entropy	68.15
		SAM	54.32
		Parallelepiped	42.52
4	Distance-based	MDC	60.39
5	Neural-based	ANN	61.69